Source data
Salesforce CRM, PSA and quoting data (opportunities, resource requests, projects, estimates, pursuit teams and schedules), read-only.
Practice operations · Weekday leadership digest · 2026
AI Practice Opportunity Radar: CRM signals delivered as actions in Microsoft Teams
Won work with nobody named puts start dates, revenue and utilization at risk. I built this service so practice leadership sees those deals every weekday morning, 2 to 10 weeks before work starts, with who to contact.
HOW IT OPERATES
Every weekday morning: a digest in Microsoft Teams. 2 to 10 weeks: the look-ahead on won deals that still need people named, including roles that call for AI skills. One case per deal: who to contact, what changed and an audit trail.
WHERE AI WAS USEDAI helped build it. Written rules run it.
I designed the service and built it in about two weeks with AI coding agents under my gated engineering process. At runtime, written rules decide which deals become cases and which send an alert. People make every staffing decision.
Fictional data. Written rules raise one case per deal; the card shows who to contact and what changed since the previous digest. Leadership makes the call.
Why it works
Nobody has to open a dashboard. The service reads the source systems, applies written rules and delivers the result to practice leadership in Microsoft Teams.
Signals, not noise
Written rules flag won work with nobody named and roles that match a configurable vocabulary of AI roles and skills, wherever the work is recorded. Each deal becomes one case, and rule tiers mean only strong matches send an alert.
Action in Teams
An Adaptive Card shows deals that need people named, people needed by month, days to first start, who to contact, what changed since the previous run and links to each deal. A shared triage queue keeps an audit trail.
Configuration
Practices, rules and vocabulary live in configuration, so adding another practice is a configuration change rather than new code.
Engineering controls
Separate test and live environments, two data paths checked for parity (Node.js with the Salesforce CLI, and Power BI), 90 automated tests, heartbeat checks and a watchdog. Power Automate delivers the cards.
Technology
- Salesforce CRM
- PSA and quoting data
- Node.js
- Salesforce CLI
- Power BI
- Power Automate
- Microsoft Teams
- Adaptive Cards
MY ROLE & SCOPE
I designed and built the service and led its rollout to practice leadership. This page describes how the service works; it does not claim measured business results. Names, clients and internal data are omitted, and the screen is a concept view with fictional data.
WHAT IT SHOWSA leadership question turned into a daily operating rhythm in about two weeks, with governance built in: read-only access, no seller names on cards, and people owning every decision.
THE NEXT CONVERSATION
Let’s talk about
the practice you want to build.
Building an AI practice takes client trust, capable people, and realistic commitments. That is the work I want to lead.
Start a conversationRead the executive brief →Based in the U.S. · Remote leadership